o1

deprecated

OpenAI's flagship reasoning model with extended chain-of-thought. Strong on math and science.

Context window200K tokens

Input / 1M tokens$15

Output / 1M tokens$60

Version History

o1-2025-09-12minorSeptember 12, 2025

o1 September update with improved tool calling reliability and expanded coverage of edge cases in mathematical reasoning.

o1-2024-12-17majorDecember 5, 2024

o1 GA release with vision, function calling, and structured outputs. Sets new records on GPQA Diamond and AIME 2024.

83.3%

AIME 2024

83.3%

AIME 2025

78.0%

GPQA

92.4%

HumanEval

72.3%

LiveCodeBench

94.8%

MATH

92.3%

MMLU

75.7%

MMLU-Pro

77.9%

MMMU

22.0 tokens_per_sec

Speed (tok/s)

48.9%

SWE-bench Verified